Search Images Maps Play YouTube News Gmail Drive More »
Sign in
Screen reader users: click this link for accessible mode. Accessible mode has the same essential features but works better with your reader.

Patents

  1. Advanced Patent Search
Publication numberUS20060069776 A1
Publication typeApplication
Application numberUS 10/941,070
Publication dateMar 30, 2006
Filing dateSep 15, 2004
Priority dateSep 15, 2004
Also published asUS7805517
Publication number10941070, 941070, US 2006/0069776 A1, US 2006/069776 A1, US 20060069776 A1, US 20060069776A1, US 2006069776 A1, US 2006069776A1, US-A1-20060069776, US-A1-2006069776, US2006/0069776A1, US2006/069776A1, US20060069776 A1, US20060069776A1, US2006069776 A1, US2006069776A1
InventorsChoon Shim, Liehua Xie
Original AssigneeShim Choon B, Liehua Xie
Export CitationBiBTeX, EndNote, RefMan
External Links: USPTO, USPTO Assignment, Espacenet
System and method for load balancing a communications network
US 20060069776 A1
Abstract
The invention relates to a system and method for load-balancing multiple servers in a communications network. Instead of using round robin or other predetermined scheme, SIP messages are forwarded to one of multiple SIP servers according to a performance score that is calculated from measured performance data. Advantageously, the disclosed system and method decreases signaling latency, improving overall communications speed. Moreover, where performance data indicates that a SIP server has failed, the performance score for the failed SIP server is zero, and the load balancer will not forward SIP messages to the failed SIP server. System uptime is also improved.
Images(16)
Previous page
Next page
Claims(26)
1. A method for load-balancing a Session Initiation Protocol (SIP) network, comprising:
receiving a SIP request from a source device;
selecting one of a plurality of SIP servers based on a plurality of performance scores, each of the plurality of performance scores associated with a corresponding one of the plurality of SIP servers; and
forwarding the SIP request to the selected SIP server.
2. The method of claim 1, further comprising:
before the selecting, determining whether the SIP request is a registration request; and
if the SIP request is a registration request, routing the SIP request to all SIP servers.
3. The method of claim 1, further comprising:
before the selecting, extracting a session signature from the SIP request;
determining whether a SIP session exists based on the extracted session signature;
if the SIP session exists, forwarding the SIP request to a SIP server associated with the existing SIP session.
4. The method of claim 1, wherein selecting one of a plurality of SIP servers includes generating a random integer; the random integer having a value greater than zero, the random integer having a value less than or equal to a sum of performance scores for the plurality of SIP servers.
5. The method of claim 4 further including identifying a server j satisfying the condition (S0+ . . . +Sj−1)<X≦(S0+ . . . +Sj), where S0, Sj−1, and Sj are the performance scores for servers 0, j−1, and j, respectively, and where X is the random integer.
6. The method of claim 1, wherein selecting one of a plurality of SIP servers includes determining the plurality of performance scores.
7. The method of claim 6, wherein determining the plurality of performance scores includes setting one of the plurality of performance scores equal to zero if a CPU usage is greater than a predetermined threshold.
8. The method of claim 6, wherein determining the plurality of performance score includes setting the performance score equal to zero if an amount of available memory is less than a predetermined threshold.
9. The method of claim 6, wherein determining the plurality of performance scores is based, at least in part, on a CPU percentage usage parameter and a memory availability parameter.
10. The method of claim 9, wherein determining the plurality of performance scores includes:
assigning a first weight to the CPU percentage usage parameter; and
assigning a second weight to the memory availability parameter.
11. The method of claim 10, wherein the determining the plurality of performance scores includes solving Si=100(W0(1−Ci)+W1Mi/ΣMk)/W0+W1), where:
Si is the performance score of an ith SIP server;
W0 is the first weight assigned to the CPU percentage usage parameter;
W1 is the second weight assigned to the memory availability parameter;
Ci is a CPU percentage usage of an ith SIP server;
Mi is an amount of available memory of the ith SIP server; and
ΣMk is a sum of available memory of the plurality of SIP servers having non-zero performance scores.
12. The method of claim 6, wherein determining the plurality of performance scores is based, at least in part, on a call volume for each of the SIP servers.
13. The method of claim 6, wherein determining the plurality of performance scores is based, at least in part, on data associated with the failure of at least one of the plurality of SIP servers.
14. A method for polling a SIP server for performance data, comprising:
receiving a data request for the performance data in a performance server;
creating a persistent performance client in the performance server;
opening a connection to an agent running on the SIP server; and
issuing a request from the persistent performance client to the agent.
15. The method of claim 14, further comprising:
receiving a reply from the agent in the performance server, the reply responsive to the request from the persistent performance client;
transmitting the reply from the performance server; and
caching the persistent performance client in the performance server.
16. A method responsive to a data request, comprising:
creating a first controller, the first controller being configured to gather and cache performance data; and
creating a server socket, the server socket being configured to determine whether a connection request has been received, the server socket being further configured to transmit the performance data.
17. The method of claim 16, further comprising creating a second controller, the second controller configured to read the performance data, the second controller further configured to determine whether the performance data exceeds a predetermined threshold, the second controller further configured to issue a notification if the performance data exceeds a predetermined threshold.
18. A method for load-balancing a Session Initiation Protocol (SIP) network, comprising:
receiving a SIP request;
generating a routing request based on the SIP request;
generating a performance score request for each of a plurality of SIP servers based on the routing request;
generating a performance data query to each of the plurality of SIP servers based on the performance score request; and
receiving the performance data query in an agent in each of the plurality of SIP servers.
19. The method of claim 18, further comprising:
responding with performance data in response to the performance data query;
calculating a performance score for each of the plurality of SIP servers based on the performance data;
selecting a SIP server from the plurality of SIP servers based on the performance score for each of the plurality of SIP servers; and
forwarding the SIP request to the selected SIP server.
20. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:
receiving a SIP request from a source device;
selecting one of a plurality of SIP servers based on a plurality of performance scores, each of the plurality of performance scores associated with a corresponding one of the plurality of SIP servers; and
forwarding the SIP request to the selected SIP server.
21. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:
receiving a data request for the performance data in a performance server;
creating a persistent performance client in the performance server;
opening a connection to an agent running on the SIP server; and
issuing a request from the persistent performance client to the agent.
22. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:
creating a first controller, the first controller being configured to gather and cache performance data; and
creating a server socket, the server socket being configured to determine whether a connection request has been received, the server socket being further configured to transmit the performance data.
23. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:
receiving a SIP request;
generating a routing request based on the SIP request;
generating a performance score request for each of a plurality of SIP servers based on the routing request;
generating a performance data query to each of the plurality of SIP servers based on the performance score request; and
receiving the performance data query in an agent in each of the plurality of SIP servers.
24. A communication system, comprising:
an interface to a source device;
a load balancer coupled to the interface;
a plurality of Session Initiation Server (SIP) servers coupled to the load balancer; and
a performance server coupled to the load balancer and the plurality of SIP servers, the performance server configured to collect performance data from the plurality of SIP servers, the load balancer configured to calculate a plurality of performance scores, each of the plurality of performance scores associated with one of the plurality of SIP servers, the plurality of performance scores based on the performance data, the load balancer further configured to direct a SIP request received from the first interface to a selected one of the plurality of SIP servers based on the plurality of performance scores.
25. The system of claim 24, wherein the load balancer includes:
a SIP forwarding module configured to forward the SIP request to the selected one of the plurality of SIP servers;
a SIP routing module coupled to the SIP forwarding module, the SIP routing module configured to select the selected one of the plurality of SIP servers based on the performance score for each of the plurality of SIP servers;
a server load computation module coupled to the SIP routing module, the server load module configured to calculate the performance score for each of the plurality of SIP servers based on the collected performance data; and
a server performance query module coupled to the server load computation module, the server performance query module configured to fetch the performance data from the performance server.
26. The system of claim 24, wherein each of the plurality of SIP servers include a performance agent, the performance agent configured to provide the performance data to the performance server.
Description
    FIELD OF INVENTION
  • [0001]
    The invention relates generally to the field of communications. More specifically, but not by way of limitation, the invention relates to a system and method for load balancing a Session Initiation Protocol (SIP) network for applications such as Voice Over Internet Protocol (VoIP) communications and Instant Messaging (IM).
  • BACKGROUND
  • [0002]
    Systems and methods are generally known for effecting signaling (control) data on a communications network. FIG. 1 is a block diagram of a functional architecture of a communications network, according to the prior art. As shown in FIG. 1, a SIP server 104 provides communications services such as routing SIP signaling messages between a source device 102 and a destination device 106. Source device 102 and/or destination device 106 may be, for example, a SIP-enabled telephone, a SIP PC (Personal Computer) client, a SIP-enabled gateway, or other device configured to originate or terminate a SIP session. FIG. 2 is a message sequence diagram of communications with a SIP server, according to the prior art. In particular, FIG. 2 illustrates signaling between the functional blocks in FIG. 1 using request and response message types: Invite and Bye are request messages; Ringing and OK are response messages.
  • [0003]
    In typical signaling applications, multiple SIP servers may be used (instead of a single SIP server 104) where the communications system also includes multiple sources and/or destination devices. But systems with multiple SIP servers have many disadvantages. For example, known systems may not be able to establish, modify, or terminate at least some SIP sessions where one or more SIP servers have failed. Moreover, requests may be received at SIP servers according to round-robin assignments or theoretical server capacity, resulting in inefficient processing of SIP messages. What is needed is a system and method for performance-based load balancing of SIP servers that can also adapt to one or more failed SIP servers in the system.
  • SUMMARY OF THE INVENTION
  • [0004]
    The invention relates to a system and method for load-balancing multiple servers in a communications network. SIP messages are forwarded to one of multiple SIP servers according to a performance score that is calculated from measured performance data from each of the multiple servers.
  • [0005]
    Embodiments of the invention provide a method for load-balancing a Session Initiation Protocol (SIP) network, including: receiving a SIP request from a source device; selecting one of a plurality of SIP servers based on a plurality of performance scores, each of the plurality of performance scores associated with a corresponding one of the plurality of SIP servers; and forwarding the SIP request to the selected SIP server.
  • [0006]
    Embodiments of the invention provide a method for polling a SIP server for performance data, including: receiving a data request for the performance data in a performance server; creating a persistent performance client in the performance server; opening a connection to an agent running on the SIP server; and issuing a request from the persistent performance client to the agent.
  • [0007]
    Embodiments of the invention provide a method responsive to a data request, including: creating a first controller, the first controller being configured to gather and cache performance data; and creating a server socket, the server socket being configured to determine whether a connection request has been received, the server socket being further configured to transmit the performance data.
  • [0008]
    Embodiments of the invention provide a method for load-balancing a Session Initiation Protocol (SIP) network, including: receiving a SIP request; generating a routing request based on the SIP request; generating a performance score request for each of a plurality of SIP servers based on the routing request; generating a performance data query to each of the plurality of SIP servers based on the performance score request; and receiving the performance data query in an agent in each of the plurality of SIP servers.
  • [0009]
    Embodiments of the invention provide a communication system, including: an interface to a source device; a load balancer coupled to the interface; a plurality of Session Initiation Server (SIP) servers coupled to the load balancer; and a performance server coupled to the load balancer and the plurality of SIP servers, the performance server configured to collect performance data from the plurality of SIP servers, the load balancer configured to calculate a performance score for each of the plurality of SIP servers based on the performance data, the load balancer further configured to direct a SIP request received from the first interface to a selected one of the plurality of SIP servers based on the performance score for each of the plurality of SIP servers.
  • [0010]
    Advantageously, the disclosed system and method decreases signaling latency, improving overall communications speed. Moreover, where performance data indicates that a SIP server has failed, the performance score for the failed SIP server is zero, and the load balancer will not forward SIP messages to the failed SIP server. So system uptime is also improved.
  • [0011]
    The features and advantages of the invention will become apparent from the following drawings and detailed description.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • [0012]
    Embodiments of the invention are described with reference to the following drawings, wherein:
  • [0013]
    FIG. 1 is a block diagram of a functional architecture of a communications network, according to the prior art;
  • [0014]
    FIG. 2 is a message sequence diagram of communications with a SIP server, according to the prior art;
  • [0015]
    FIG. 3 is a block diagram of a functional architecture of a communications network, according to an embodiment of the invention;
  • [0016]
    FIG. 4 is a block diagram of a functional architecture of the SIP load balancer in FIG. 3, according to an embodiment of the invention;
  • [0017]
    FIG. 5 is a flow diagram of a routing/forwarding process, according to an embodiment of the invention;
  • [0018]
    FIG. 6 is a flow diagram of a server selection process, according to an embodiment of the invention;
  • [0019]
    FIG. 7 is a graphical illustration of a server selection plot, according to an embodiment of the invention;
  • [0020]
    FIG. 8 is a flow diagram of a process for calculating server load, according to an embodiment of the invention;
  • [0021]
    FIG. 9 is a graphical illustration of server load scores, according to an embodiment of the invention;
  • [0022]
    FIG. 10 is a flow diagram of a server performance query process, according to an embodiment of the invention;
  • [0023]
    FIG. 11 is a block diagram of a functional architecture for collecting performance data, according to an embodiment of the invention;
  • [0024]
    FIG. 12 is a flow diagram of a polling process from the perspective of a performance server, according to an embodiment of the invention;
  • [0025]
    FIG. 13 is a flow diagram for a polling process from the perspective of a performance agent on a SIP server, according to an embodiment of the invention;
  • [0026]
    FIG. 14 is a block diagram of a test bed functional architecture, according to an embodiment of the invention; and
  • [0027]
    FIG. 15 is an illustration of a test results table, according to an embodiment of the invention.
  • DETAILED DESCRIPTION
  • [0028]
    This section provides a top-level functional architecture, exemplary selection, routing and forwarding processes, a process for calculating a performance score, a process for collecting performance data, and a summary of empirical analysis. Sub-headings are used below for organizational convenience. The disclosure of any particular feature is not necessarily limited to any particular section, however.
  • [0000]
    Top Level Functional Architecture
  • [0029]
    FIG. 3 is a block diagram of a functional architecture of a communications network, according to an embodiment of the invention. As shown in FIG. 4, a functional architecture includes source device 102, load balancer 302, performance server 304, SIP servers 306A, 306B, 306C, and 306D, a network 308, and a destination device 106. The load balancer 302 is coupled to the source device 102, the performance server 304, and each of the SIP servers 306A, 306B, 306C, and 306D. The performance server 405 is also coupled to each of the SIP servers 306A, 306B, 306C, and 306D. Further, network 308 is coupled to each of the SIP servers 306A, 306B, 306C, and 306D and the destination device 106.
  • [0030]
    The load balancer 302, performance server 304, SIP servers 306A, 306B, 306C, and 306D may each include a processor, each of the processors being configured to read and execute instructions from a processor-readable storage medium. In one variation, the load balancer 302 and the performance server 304 share a processor. The storage medium may be or include, for instance, a hard drive, Random Access Memory (RAM), or a Computer Disc (CD) Read Only memory (ROM). The load balancer 302, performance server 304, SIP servers 306A, 306B, 306C, and 306D may each be configured, for example, with a server operating system, examples of which include Linux™ or Windows™ server operating systems. SIP servers 306A, 306B, 306C and 306D may each be configured as SIP proxy servers.
  • [0031]
    The load balancer 302 is configured to receive a SIP message from source device 102. Informed by the performance server 304, the load balancer 302 is configured to forward the SIP message from the source device 102 to a selected one of the SIP servers 306A, 306B, 306C, and 306D. In turn, the selected SIP server establishes a session between the source device 102 and the destination device 106.
  • [0032]
    Variations of the functional architecture illustrated in FIG. 3 are also contemplated. For example, although four SIP servers are illustrated in FIG. 3, a functional architecture may have two or more SIP servers. Further, in a general case, a functional architecture may include multiple source devices and/or multiple destination devices. Moreover, switches or servers configured for H.323 or other IP telephony or other communications protocol could be used in the alternative to, or in combination with, the illustrated SIP servers 306A, 306B, 306C, and 306D, according to design choice.
  • [0033]
    FIG. 4 is a block diagram of a functional architecture of the SIP load balancer in FIG. 3, according to an embodiment of the invention. As shown therein, an exemplary load balancer 302 includes SIP forwarding module 402, SIP routing module 404, server load computation module 406, and server performance query module 408. The SIP routing module 404 is coupled to the SIP forwarding module 402 and the server load computation module 406. The server load computation module 406 is coupled to the SIP routing module 404 and the server performance query module 408. The server performance query module 408 is coupled to the server load computation module 406. In the illustrated embodiment, each of the couplings described above are two-way couplings.
  • [0034]
    The SIP forwarding module 402 is configured to receive a SIP request from the source device 102 and send an inquiry to the SIP routing module 404 to determine a SIP server recipient of the SIP message. Once the SIP forwarding module 402 receives the SIP server selection from the SIP routing module 404, the SIP forwarding module 402 is configured to forward the SIP request to the selected SIP server (e.g., one of SIP servers 306A, 306B, 306C, and 306D).
  • [0035]
    In response to a routing inquiry from the SIP forwarding module 402, the SIP routing module 404 is configured to request performance scores from the server load computation module 406, to select a SIP server (e.g., one of SIP servers 306A, 306B, 306C, and 306D) based on the performance scores, and forward the selection to the SIP forwarding module 402.
  • [0036]
    The server load computation module 406 is configured to receive a request for performance scores from the SIP routing module 404, request performance data from the server performance query module 408, calculate a performance score for each of the SIP servers 306A, 306B, 306C, and 306D based on the performance data, and provide the performance scores to the SIP routing module 404.
  • [0037]
    The server performance query module 408 is configured to receive a request for performance data from the server load computation module 406, solicit performance data from the performance server 304, and forward the performance data to the server load computation module 406.
  • [0038]
    Variations to the functional architecture illustrated in FIG. 4 are possible. For example, any of the functional capability illustrated therein and described above may be combined in functional groupings different from that illustrated in FIG. 4 and described above.
  • [0039]
    In operation, data may be cached or otherwise stored at various locations of the functional architecture. For instance, in response to a request for performance scores, server load computation module 406 may provide most recent performance scores to the SIP routing module 404 without having to first initiate a request for server performance data from the server performance query module 408. Likewise, in response to a request from the server load computation module 406, the server performance query module 408 may provide most recent server performance data to the server load computation module 406 prior to sending a request to the performance server 304.
  • [0040]
    Embodiments of processes performed by the functional components of the load balancer 302 are further described with reference to FIGS. 5-10 below.
  • [0000]
    Selection, Routing, and Forwarding Processes
  • [0041]
    FIG. 5 is a flow diagram of a routing/forwarding process, according to an embodiment of the invention. As shown therein, the process begins by receiving a SIP request in step 502. The process then advances to conditional step 504 to determine whether the received request is a registration request. Where the result of conditional step 504 is in the affirmative, the process advances to step 506 to route the SIP request to all SIP servers. In an alternative embodiment, if the result of conditional step 504 is in the affirmative, the process routes the SIP request to a registrar server (step not shown).
  • [0042]
    On the other hand, where the result of conditional step 504 is in the negative, the process is promoted to step 508 to extract a session signature from the SIP request in step 508. The execution of step 508 may vary according to proprietary SIP implementation schemes. Then, in conditional step 510, the process determines whether a SIP session exists (e.g., based on the session signature). If it is determined in conditional step 510 that a SIP session exists (e.g., the SIP request is associated with an existing SIP session), then the process advances to step 512 to forward the SIP request to the (pre)selected SIP server associated with the existing SIP session. Accordingly, a SIP request associated with an active session is simply routed to the appropriate SIP server.
  • [0043]
    If it is determined in conditional step 510 that a SIP session does not exist (e.g., the request is associated with a new SIP session), then the process selects a SIP server in step 514 and advances to conditional step 516 to determine whether the selected SIP server has been found. Where the result of conditional step 516 is in the negative, the process advances to step 518 to drop (e.g., terminate processing of) the SIP request. Where the result of conditional step 516 is in the affirmative, the process advances to step 512 to forward the SIP request to the (newly) selected SIP server. Accordingly, a SIP request associated with a new session requires selection of a SIP server in step 514 before being forwarded to the selected SIP server in step 512. The load balancer 302 preferably maintains a list of active SIP sessions to execute conditional step 510 described above.
  • [0044]
    Variations to the process illustrated in FIG. 5 are contemplated. For example, conditional step 504 and associated step 506 are optional. In addition, conditional step 514 may be considered a portion of selection step 516.
  • [0045]
    FIG. 6 is a flow diagram of a server selection process, according to an embodiment of the invention. In other words, FIG. 6 is one embodiment of selection step 514. As shown therein, the process begins in step 602, then advances to step 604 to generate a random integer X, where 0<X≦ΣSk. ΣSk is the sum of performance scores for all SIP servers (shown graphically on integer axis 702 of FIG. 7).
  • [0046]
    Next, j is set equal to zero in step 606, and conditional step 608 tests whether (S0+ . . . +Sj−1)<X≦(S0+ . . . Sj). S0, Sj−1, and Sj are the performance scores for servers 0 (S0), j−1, and j, respectively. If the result of conditional step 608 is negative, then the value of j is incremented by 1 in step 610, and the process returns to conditional step 608. If the result of conditional step 608 is positive, then the process selects server j in step 612.
  • [0047]
    Accordingly, the server selection process 514 illustrated in FIG. 6 tests one or more servers in steps 606, 608, and 610 to associate random integer X with a particular server j. The exemplary process illustrated in FIG. 6 can be further understood with reference to the server selection plot illustrated in FIG. 7.
  • [0048]
    FIG. 7 is a graphical illustration of a server selection plot, according to an embodiment of the invention. As shown in FIG. 7, data for each of five servers, S0, S1, S2, S3, and S4 are plotted on integer axis 702 and score axis 704. The integer axis 702 is divided into N partitions sequentially assigned to servers S0, S1, S2, S3, and S4. For each server, the size of the partition along integer axis 702 is proportional to the performance score.
  • [0049]
    FIG. 7 further illustrates the position on the integer axis 702 for a random integer X generated in step 604. It should be apparent that the larger the performance score for a server, the larger the partition size, and the more likely that the random integer X will be associated with a server having a relatively larger performance score. It would be determined in step 608 (with reference to integer axis 702) that (S0+S1)<X≦(S0+S1+S2). Thus, server S2 would be selected.
  • [0050]
    The performance score S3 associated with server S3 is represented by a single point on the integer axis 702. Note that the selection criteria in conditional step 608 prevents selection of a server having a performance score of zero. For example, if random integer X were equal to S0+S1+S2, the point where it is indicated in FIG. 7 that the performance score for server S3 is equal to zero, server S2 would be selected by the process depicted in FIG. 6.
  • [0051]
    As described above, calculation of a performance score for each of the SIP servers is a prerequisite to selecting a SIP server in step 514.
  • [0000]
    Calculating a Performance Score
  • [0052]
    FIG. 8 is a flow diagram of a process for calculating server load (or performance score), according to an embodiment of the invention. As shown therein, the process begins in step 802, then advances to step 804 to read each of several parameters. For example, in step 804, the process reads Ci, which is the Computer Processing Unit (CPU) usage, expressed as a percentage, for the ith SIP server. The process also reads Cmax, which is the maximum CPU usage, also expressed as a percentage. Also in step 804, the process may read Mi, which is the amount of available memory of the ith SIP server, expressed as a percentage of total memory. Further, in step 804, the process reads Mmin, which is the minimum required memory (again, expressed as a percentage of total memory). The process may also read or calculate ΣMk, which is the sum of the available memory for all SIP servers with a non-zero performance score. Finally, in step 804, the process may read W0 and W1, which are the predetermined weight of the CPU usage percentage parameter and the predetermined weight of the memory availability parameter, respectively. In one embodiment, Cmax is 95%, Mmin is 10 Mbytes, and W0 and W1 are both set equal to 1.
  • [0053]
    After reading the parameters in step 804, the process advances to conditional step 806 where it is determined whether Ci is less than or equal to Cmax. Where the result of conditional step 806 is in the affirmative, the process advances to step 810 to determine whether Mi is greater or equal to Mmin. Where the result of either conditional step 806 or conditional step 810 are in the negative, the process terminates in step 808, where a performance score Si is set equal to zero. Where the result of conditional step 810 is in the affirmative, the process advances to step 812 to calculate the performance score Si given by: Si=100(W0(1−Ci)+WiMi/ΣMk)/W0+W1). Advantageously, scoring sensitivity can be adjusted by varying the predetermined weights W0 and W1 according to application requirements.
  • [0054]
    FIG. 9 is a graphical illustration of server performance scores 902, according to an embodiment of the invention. As shown, the highest performance score, 100%, is the case where CPU usage (Ci) is 0%, and memory availability (Mi) is 100%. As CPU and/or memory resources become less available, the performance score drops. Where the CPU usage (Ci) is 100%, and/or where the memory availability (Mi) is 0%, the performance score is equal to zero. In the illustrated embodiment, W0 and W1 are both set equal to 1. In alternative embodiments, the scoring solution can be made more sensitive to either memory availability or CPU utilization by changing the value of W0 and/or W1 either off-line or in-situ.
  • [0055]
    In alternative embodiments of the invention, the above calculation may be performed without a CPU usage parameter, or without a memory availability parameter. Moreover, in other embodiments, performance scores may be calculated based on network utilization, call volume, failure statistics (such as indications of server down status, or abnormal SIP session terminations), and/or other factors either separately or combined with CPU usage and/or memory availability so that multiple SIP servers can be load balanced based on one or more performance metrics, and/or so that fault tolerance can be provided to a SIP-based application.
  • [0000]
    Collecting Performance Data
  • [0056]
    FIG. 10 is a flow diagram of a server performance query process, according to an embodiment of the invention. As shown in FIG. 10, the process begins in step 1002, and then advances to step 1004 to set a parameter N equal to 1. Next, the process advances to step 1006 to poll a server PSN (the Nth SIP server). Then, the process advances to conditional step 1008 to determine whether the data being polled in step 1006 has been received. Where the result of conditional step 1008 is in the affirmative, the process advances to step 1012 to determine whether the query process of FIG. 10 is completed. If the result of conditional step 1012 is in the affirmative, the process terminates in step 1016.
  • [0057]
    Where the result of conditional step 1008 is in the negative, the process associates PSN with a down condition, and the process continues at conditional step 1012. Where the result of conditional step 1012 is in the negative, the process advances to step 1014 where the server number is incremented by a 1 and the process returns to polling step 1006.
  • [0058]
    Accordingly, the process illustrated in FIG. 10 can be executed by the server performance query module 408 to collect server performance data for each of N SIP servers. FIGS. 11-13 illustrate one embodiment for retrieving the performance data being polled in step 1006.
  • [0059]
    FIG. 11 is a block diagram of a functional architecture for collecting performance data, according to an embodiment of the invention. As shown in FIG. 11, performance server 304 is coupled to performance agent 1102 in SIP server 306A and to performance agent 1104 in SIP server 306B.
  • [0060]
    FIG. 12 is a flow diagram of a polling process from the perspective of a performance server, according to an embodiment of the invention. As shown in FIG. 12, the process begins in step 1202 where performance server 304 receives a SIP request from load balancer 302 for a specific SIP server (e.g., SIP server 306A or SIP server 306B) or other node. Next, the process advances to step 1204 where the performance server 304 creates a persistent performance client (PPC) for the specified node. Next, the process advances to step 1206 where the PPC opens a connection to an agent (e.g., performance agent 1102 or performance agent 1104) running on the specified node. Then, in step 1208, the PPC issues a “get data” request to the agent. Next, in step 1210, the PPC receives and processes a reply from the agent. Then, in step 1212, the performance server 304 sends a performance statistics to the load balancer 302. Finally, in step 1214 the performance server 304 caches the PPC.
  • [0061]
    Thus, in one embodiment of the invention, performance data is collected by one or more performance servers using agents that are embedded in each of the SIP servers.
  • [0062]
    FIG. 13 is a flow diagram for a polling process from the perspective of a performance agent on a SIP server, according to an embodiment of the invention. As illustrated in FIG. 13, upon receipt of an initiation in step 1302, the process launches three separate and distinct processes: a create collection controller step 1304, a create server socket step 1312, and a create notification controller step 1322.
  • [0063]
    In response to the create collection controller step 1304, the process advances to gather performance data in step 1306, then cache performance data in 1308. After step 1308, the process may advance to a delay step 1310 before returning to step 1306 to gather additional performance data.
  • [0064]
    Subsequent to creating the server socket in step 1312, the process advances to conditional step 1314 to determine whether a connection request has been received from the performance server 304. Where the result of conditional step 1314 is in the affirmative, the process advances to step 1316 to create a new worker object. Next, in step 1318, the process receives a “get data” request from the performance server 304. Then, in step 1320, the process returns the performance data (which was gathered in step 1306 and cached in step 1308) to the performance server 304. Where the result of conditional step 1314 is in the negative, the process returns to conditional step 1314.
  • [0065]
    In response to the creation of a notification controller in step 1322, the process advances to step 1324 to read the performance data cached in step 1308. Next, the process advances to conditional step 1326 to determine whether the performance data exceeds a predetermined threshold. For example, a CPU utilization threshold may be set at 85%, and a memory availability threshold may be set at 10 MB. Where the result of step 1326 is in the affirmative, the process issues a notification to the performance server 304 in step 1328. Where the data does not exceed a pre-determined threshold in conditional step 1326, the process returns to step 1324 to read performance data.
  • [0066]
    Variations to the process illustrated in FIG. 13 are contemplated. For example, the implementation of delay step 1310 is optional. In addition, where the result of conditional step 1314 is in the negative, an optional delay step could be inserted before returning to conditional step 1314.
  • [0000]
    Empirical Analysis
  • [0067]
    Embodiments of the invention described above were tested using the architecture illustrated in FIG. 14. The test produced the results summarized in FIG. 15.
  • [0068]
    FIG. 14 is a block diagram of a test bed functional architecture, according to an embodiment of the invention. As shown, SIP telephones 1402 and 1404, softphones 1406 and 1408, Load balancer 1412, and SIP proxy servers 1414 and 1416 were coupled via link 1410. SIP telephones 1402 and 1404 were 3Com® SIP telephones, and softphones 1406 and 1408 were implemented with Microsoft Windows® Messenger running on laptop personal computers.
  • [0069]
    To initialize the test, SIP telephones 1402 and 1404, and softphones 1406 and 1408 were each registered with SIP proxy servers 1414 and 1416. Server 1414 was assigned address 10.10.1.213, and server 1416 was assigned address 10.10.1.208. In addition, phones 1402, 1404, 1406, and 1408 were each configured with load balancer 1412 address 10.10.1.221 as the outbound proxy address. A software tool was used to generate a controlled load on each of the SIP proxy servers 1414 and 1416, while signaling messages were generated using phones 1402, 1404, 1406, and 1408. Log messages in load balancer 1412 were later reviewed to determine the number of times that each SIP proxy server 1414 and 1416 were selected.
  • [0070]
    FIG. 15 is an illustration of a test results table, according to an embodiment of the invention. As shown therein, the test included four scenarios, 1-4.
  • [0071]
    In scenario 1, server 1414 and server 1416 were lightly loaded; the result was that the performance scores were similar, and load balancer 1412 selected servers 1414 and 1416 more or less equally. In scenario 2, server 1414 was heavily loaded, and server 1416 was lightly loaded; the result was that server 1416 was selected 17 out of 20 times. In scenario 3, server 1414 was lightly loaded, and server 1416 was heavily loaded; the result was that server 1414 was selected 15 out of 20 times. In scenario 4, server 1414 and server 1416 were both heavily loaded; the result was that servers 1414 and 1416 were selected more or less equally.
  • CONCLUSION
  • [0072]
    The invention described above thus overcomes the disadvantages of known systems and methods by balancing signaling load amongst multiple servers based on performance scores calculated from measured performance data. While this invention has been described in various explanatory embodiments, other embodiments and variations can be effected by a person of ordinary skill in the art without departing from the scope of the invention. For example, the systems and methods described herein could be applied to different signaling protocols or communication environments.
Patent Citations
Cited PatentFiling datePublication dateApplicantTitle
US5805824 *Feb 28, 1996Sep 8, 1998Hyper-G Software Forchungs-Und Entwicklungsgesellschaft M.B.H.Method of propagating data through a distributed information system
US5951694 *Feb 3, 1997Sep 14, 1999Microsoft CorporationMethod of redirecting a client service session to a second application server without interrupting the session by forwarding service-specific information to the second server
US6185619 *Nov 7, 1997Feb 6, 2001Genuity Inc.Method and apparatus for balancing the process load on network servers according to network and serve based policies
US6279001 *May 29, 1998Aug 21, 2001Webspective Software, Inc.Web service
US6330707 *Sep 21, 1998Dec 11, 2001Matsushita Electric Industrial Co., Ltd.Automatic routing method
US6829643 *Nov 20, 2000Dec 7, 2004Fujitsu LimitedNetwork control apparatus having bandwidth control method selection associated to users utilizing status tables, ranking tables, and total points of user's information parameters
US7050963 *Sep 12, 2001May 23, 2006Progress Software CorporationMethod and apparatus for flash load balancing
US7103809 *Oct 24, 2003Sep 5, 2006Motorola, Inc.Server selection method
US7123700 *Apr 27, 2000Oct 17, 2006Nortel Networks LimitedConfiguring user interfaces of call devices
US7292531 *Dec 31, 2002Nov 6, 2007Packeteer, Inc.Methods, apparatuses and systems facilitating analysis of the performance of network traffic classification configurations
US7305562 *Mar 1, 2000Dec 4, 2007Citibank, N.A.System, method and computer program product for an authentication management infrastructure
US7308475 *May 6, 2003Dec 11, 2007F5 Networks, Inc.Method and system for accessing network services
US7340598 *Jul 9, 2004Mar 4, 2008Computer Associates Think, Inc.Method and system for monitoring a computer system for dynamic reconfiguration
US7363378 *Jul 1, 2003Apr 22, 2008Microsoft CorporationTransport system for instant messaging
US7475108 *Jun 16, 2004Jan 6, 2009International Business Machines CorporationSlow-dynamic load balancing method
US7565656 *Jul 20, 2004Jul 21, 2009Hitachi, Ltd.System, method and program for allocating computer resources
US20020038331 *Sep 12, 2001Mar 28, 2002Flavin James D.Method and apparatus for flash load balancing
US20020090132 *Nov 5, 2001Jul 11, 2002Boncyk Wayne C.Image capture and identification system and process
US20020152305 *Jan 30, 2002Oct 17, 2002Jackson Gregory J.Systems and methods for resource utilization analysis in information management environments
US20020174220 *May 21, 2001Nov 21, 2002Johnson Teddy ChristianMethods and structure for reducing resource hogging
US20020194326 *Jun 12, 2001Dec 19, 2002Stephen GoldUser capacity limit algorithm for computer entity
US20030037145 *Jan 30, 2001Feb 20, 2003Michael FaganApparatus and method of allocating communications resources
US20030046412 *Aug 28, 2002Mar 6, 2003Nec CorporationContent delivery system using a proxy content server
US20030051187 *Aug 9, 2001Mar 13, 2003Victor MashayekhiFailover system and method for cluster environment
US20040024879 *Jul 30, 2002Feb 5, 2004Dingman Christopher P.Method and apparatus for supporting communications between a computing device within a network and an external computing device
US20040073639 *Sep 6, 2002Apr 15, 2004Tony BasogluMethod of load balancing across two or more servers in a computer network
US20040103194 *Nov 21, 2002May 27, 2004Docomo Communicatios Laboratories Usa, Inc.Method and system for server load balancing
US20040153549 *Nov 28, 2001Aug 5, 2004Akihiko NaitoInternet communication system
US20040215787 *Apr 15, 2004Oct 28, 2004Gibson Mark RobertEstablishing connections across a communications network
US20050027862 *Jul 18, 2003Feb 3, 2005Nguyen Tien LeSystem and methods of cooperatively load-balancing clustered servers
US20050038890 *Feb 23, 2004Feb 17, 2005Hitachi., Ltd.Load distribution method and client-server system
US20050038989 *Jul 9, 2004Feb 17, 2005Computer Associates Think, IncMethod and system for monitoring a computer system for dynamic reconfiguration
US20050066328 *Sep 23, 2003Mar 24, 2005Lam Siu H.Method and apparatus to perform task scheduling
US20050216729 *Mar 29, 2004Sep 29, 2005Joels Jo AHealth reporting mechanism for inter-network gateway
US20050268155 *Jul 25, 2005Dec 1, 2005Dell Products L.P.Failover system and method for cluster environment
US20050268156 *Jul 25, 2005Dec 1, 2005Dell Products L.P.Failover system and method for cluster environment
US20070160033 *Jun 29, 2004Jul 12, 2007Marjan BozinovskiMethod of providing a reliable server function in support of a service or a set of services
US20070260676 *Jun 29, 2004Nov 8, 2007Marjan BozinovskiMethod Of Selecting One Server Out Of A Server Set
US20090024425 *Jul 17, 2007Jan 22, 2009Robert CalvertMethods, Systems, and Computer-Readable Media for Determining an Application Risk Rating
Referenced by
Citing PatentFiling datePublication dateApplicantTitle
US7631093Dec 8, 2009TekelecScalable, reliable session initiation protocol (SIP) signaling routing node
US7742421Jul 31, 2008Jun 22, 2010TekelecSystems, methods, and computer program products for distributing application or higher layer communications network signaling entity operational status information among session initiation protocol (SIP) entities
US7929419 *Aug 25, 2006Apr 19, 2011TekelecMethods, systems, and computer program products for inhibiting message traffic to an unavailable terminating SIP server
US7953877May 15, 2006May 31, 2011Oracle International CorporationSystem and method for controlling data flow based upon a temporal policy
US7954005 *Feb 2, 2010May 31, 2011Oracle International CorporationSIP server architecture for improving latency during message processing
US7957403Jun 7, 2011Oracle International CorporationSystem and method for controlling access to legacy multimedia message protocols based upon a policy
US8001250Aug 16, 2011Oracle International CorporationSIP and HTTP convergence in network computing environments
US8078737Dec 13, 2007Dec 13, 2011Oracle International CorporationSystem and method for efficient storage of long-lived session state in a SIP server
US8112525Feb 7, 2012Oracle International CorporationEngine near cache for reducing latency in a telecommunications environment
US8161125Apr 17, 2012Microsoft CorporationMessage data management
US8171466 *May 15, 2007May 1, 2012Oracle International CorporationHitless application upgrade for SIP server architecture
US8219697May 17, 2007Jul 10, 2012Oracle International CorporationDiameter protocol and SH interface support for SIP server architecture
US8230032Jul 24, 2012Microsoft CorporationMessage data management
US8453241May 28, 2013Illinois Institute Of TechnologyMethod for securing streaming multimedia network transmissions
US8463907 *Dec 8, 2006Jun 11, 2013Samsung Sds Co., Ltd.System and method for performance test in outside channel combination environment
US8498202Feb 11, 2011Jul 30, 2013Tekelec, Inc.Methods, systems, and computer readable media for diameter network management
US8626934May 15, 2006Jan 7, 2014Oracle International CorporationSystem and method for controlling access to legacy push protocols based upon a policy
US8768350Dec 9, 2004Jul 1, 2014Level 3 Communications, LlcSystems and methods for locating endpoints in a communication network
US8976783 *Dec 19, 2007Mar 10, 2015At&T Intellectual Property I, L.P.Method and apparatus for assuring voice over internet protocol service
US9020105Jun 7, 2010Apr 28, 2015Level 3 Communications, LlcSystems and methods for third party emergency call termination
US9071512Aug 3, 2011Jun 30, 2015Tekelec, Inc.Methods, systems, and computer readable media for distributing diameter network management information
US9088599 *Dec 23, 2011Jul 21, 2015Level 3 Communications, LlcRegistration redirect server
US9106769Aug 10, 2012Aug 11, 2015Tekelec, Inc.Methods, systems, and computer readable media for congestion management in a diameter signaling network
US9148482Aug 26, 2014Sep 29, 2015Blackberry LimitedSystem and method for SIP user agent identification and efficient binding
US9191447Aug 7, 2014Nov 17, 2015Blackberry LimitedSystem and method for applying authentication and security policies in a SIP environment
US9235448 *Nov 25, 2008Jan 12, 2016Citrix Systems, Inc.Systems and methods for batchable hierarchical configuration
US9317333 *Oct 30, 2007Apr 19, 2016Vmware, Inc.Method and system for providing load balancing for virtualized application workspaces
US9391897Jul 31, 2013Jul 12, 2016Oracle International CorporationMethods, systems, and computer readable media for mitigating traffic storms
US20050147087 *Feb 25, 2005Jul 7, 2005TekelecScalable, reliable session intiation protocol (SIP) signaling routing node
US20050157707 *Feb 25, 2005Jul 21, 2005TekelecScalable, reliable session initiation protocol (SIP) signaling routing node
US20060064478 *Nov 10, 2005Mar 23, 2006Level 3 Communications, Inc.Geo-locating load balancing
US20070094336 *Oct 24, 2005Apr 26, 2007Microsoft CorporationAsynchronous server synchronously storing persistent data batches
US20070106799 *May 15, 2006May 10, 2007Bea Systems, Inc.System and method for controlling access to legacy multimedia message protocols based upon a policy
US20070106808 *May 15, 2006May 10, 2007Bea Systems, Inc.System and method for controlling data flow based upon a temporal policy
US20070203983 *Feb 15, 2007Aug 30, 2007Fujitsu LimitedServer
US20080019812 *Jul 19, 2006Jan 24, 2008Dennis MoryskiCab-over loading frame
US20080056234 *Aug 25, 2006Mar 6, 2008TekelecMethods, systems, and computer program products for inhibiting message traffic to an unavailable terminating SIP server
US20080091837 *May 15, 2007Apr 17, 2008Bea Systems, Inc.Hitless Application Upgrade for SIP Server Architecture
US20080140826 *Mar 12, 2007Jun 12, 2008Microsoft CorporationMonitoring and controlling electronic message distribution
US20080147524 *Dec 13, 2007Jun 19, 2008Bea Systems, Inc.System and Method for a SIP Server with Offline Charging
US20080147551 *Dec 13, 2007Jun 19, 2008Bea Systems, Inc.System and Method for a SIP Server with Online Charging
US20080147787 *Oct 30, 2007Jun 19, 2008Wilkinson Anthony JMethod and system for providing load balancing for virtualized application workspaces
US20080148405 *Dec 18, 2006Jun 19, 2008Carol DavidsMethod for securing streaming multimedia network transmissions
US20080189421 *May 15, 2007Aug 7, 2008Bea Systems, Inc.SIP and HTTP Convergence in Network Computing Environments
US20090006598 *Dec 13, 2007Jan 1, 2009Bea Systems, Inc.System and Method for Efficient Storage of Long-Lived Session State in a SIP Server
US20090019158 *May 15, 2007Jan 15, 2009Bea Systems, Inc.Engine Near Cache for Reducing Latency in a Telecommunications Environment
US20090040923 *Jul 31, 2008Feb 12, 2009Apirux BantukulSystems, methods, and computer program products for distributing application or higher layer communications network signaling entity operational status information among session initiation protocol (sip) entities
US20090070877 *Nov 17, 2008Mar 12, 2009Carol DavidsMethod for securing streaming multimedia network transmissions
US20090161657 *Dec 19, 2007Jun 25, 2009Li-Jin ChungMethod and apparatus for assuring voice over internet protocol service
US20090238168 *Mar 18, 2008Sep 24, 2009Paraxip Technologies Inc.Communication node and method for handling sip communication
US20090310484 *Apr 17, 2009Dec 17, 2009Dorgham SisalemMethods, systems, and computer readable media for session initiation protocol (sip) overload control
US20100017657 *Dec 8, 2006Jan 21, 2010Samsung Sds Co., Ltd.System and Method for Performance Test in Outside Channel Combination Environment
US20100131620 *Nov 25, 2008May 27, 2010Ravi KondamuruSystems and methods for batchable hierarchical configuration
US20100205263 *Aug 12, 2010Bea Systems, Inc.Sip server architecture for improving latency during message processing
US20100248683 *Jun 7, 2010Sep 30, 2010Level 3 Communications, Inc.Systems and Methods for Third Party Emergency Call Termination
US20110154016 *Jun 18, 2008Jun 23, 2011Nec Europe Ltd.Method for aggregating information values in a network
US20110185027 *Jul 28, 2011Microsoft CorporationMessage data management
US20110185281 *Jul 28, 2011Microsoft CorporationMessage data management
US20120259986 *Apr 5, 2012Oct 11, 2012Research In Motion LimitedSystem and method to preserve dialogs in clustered environments in case of node failure
US20130060941 *Dec 23, 2011Mar 7, 2013Level 3 Communications, Inc.Registration Redirect Server
US20150200820 *Mar 13, 2013Jul 16, 2015Google Inc.Processing an attempted loading of a web resource
US20160094643 *Dec 1, 2014Mar 31, 2016Nicira, Inc.Dynamically adjusting load balancing
EP2069954A2 *Aug 3, 2007Jun 17, 2009TekelecMethod, systems, and computer program products for inhibiting message traffic to an unavailable terminating sip server
EP2069954A4 *Aug 3, 2007Dec 18, 2013Tekelec IncMethod, systems, and computer program products for inhibiting message traffic to an unavailable terminating sip server
EP2095585A4 *Dec 7, 2007Apr 13, 2016Cisco Tech IncScalability of providing packet flow management
EP2122480A1 *Mar 13, 2008Nov 25, 2009Radvision LtdMethods, media, and systems for balancing session initiation protocol server load
WO2007138398A1 *Apr 30, 2007Dec 6, 2007Nokia Siemens Networks OyAllocation of a call state control function to a subscriber
WO2008019056A2Aug 3, 2007Feb 14, 2008TekelecInhibiting message traffic to an unavailable terminating sip server
WO2008080635A1 *Jan 3, 2007Jul 10, 2008Telefonaktiebolaget Lm Ericsson (Publ)Test phone using sip
WO2016075671A1 *Nov 13, 2015May 19, 2016Telefonaktiebolaget L M Ericsson (Publ)Elasticity for highly availabile applications
Classifications
U.S. Classification709/225
International ClassificationG06F15/173
Cooperative ClassificationH04L67/1008, H04L67/1012, H04L67/1002
European ClassificationH04L29/08N9A1D, H04L29/08N9A1B, H04L29/08N9A
Legal Events
DateCodeEventDescription
Mar 14, 2005ASAssignment
Owner name: QOVIA, INC., MARYLAND
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SHIM, CHOON B.;XIE, LEIHUA;REEL/FRAME:015894/0562
Effective date: 20050118
Dec 6, 2007ASAssignment
Owner name: CISCO SYSTEMS, INC., CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:QOVIA, INC.;REEL/FRAME:020208/0156
Effective date: 20070202
Owner name: CISCO SYSTEMS, INC.,CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:QOVIA, INC.;REEL/FRAME:020208/0156
Effective date: 20070202
Apr 25, 2008ASAssignment
Owner name: CISCO TECHNOLOGY, INC., CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CISCO SYSTEMS, INC.;REEL/FRAME:020860/0257
Effective date: 20071210
Owner name: CISCO TECHNOLOGY, INC.,CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CISCO SYSTEMS, INC.;REEL/FRAME:020860/0257
Effective date: 20071210
Nov 30, 2010CCCertificate of correction
Mar 28, 2014FPAYFee payment
Year of fee payment: 4